Image Recognition with Occlusions

We study the problem of how to detect \interesting objects" appeared in a given image, I. Our approach is to treat it as a function approximation problem based on an over-redundant basis. Since the basis (a library of image templates) is over-redundant, there are in nitely many ways to decompose I. To select the \best" decomposition we rst propose a global optimization procedure that considers a concave cost function derived from a \weighted Lp

• Type: Conference
• Year: 1996
• Where: ECCV
• Authors: Tyng-Luh Liu, Michael J. Donahue, Davi Geiger, Robert A. Hummel
• Keywords: Computer Vision, Concave Cost Function, ECCV 1996, Function Approximation Problem, Global Optimization Procedure